Reinforcement Learning Game

An interactive demonstration of AI agents learning to play.

Game Arena

0.10
Controls how much the agent updates its Q-values based on new information. Higher values mean faster learning but potentially more instability.?
0.95
Determines the importance of future rewards. A value closer to 1 means the agent values future rewards more.?
0.10
Controls the probability of the agent choosing a random action (exploration) instead of the best-known action (exploitation). Starts high and decays over time.?
The number of times the agent will play the game from start to finish to learn.?
Ready to train.

About the Game & AI

This is a simple grid-world environment where an AI agent learns to navigate from a starting point to a goal. The agent can move up, down, left, or right. The objective is to reach the goal state efficiently, minimizing steps and avoiding potential pitfalls (if implemented).

The agent utilizes the Q-learning algorithm, a popular form of reinforcement learning. It learns a Q-table, which maps state-action pairs to expected future rewards. Through trial and error, guided by exploration and exploitation, the agent refines its strategy to maximize its cumulative reward.

Key Concepts: